Inconsistencies on TripAdvisor reviews: A unified index between users and Sentiment Analysis Methods

TripAdvisor is an opinion source frequently used in Sentiment Analysis. On this social network, users explain their experiences in hotels, restaurants or touristic attractions. They write texts of 200 character minimum and score the overall of their review with a numeric scale that ranks from 1 (Terrible) to 5 (Excellent). In this work, we aim that this score, which we define as the User Polarity, may not be representative of the sentiment of all the sentences that make up the opinion. We analyze opinions from six Italian and Spanish monument reviews and detect that there exist inconsistencies between the User Polarity and Sentiment Analysis Methods that automatically extract polarities. The fact is that users tend to rate their visit positively, but in some cases negative sentences and aspects appear, which are detected by these methods. To address these problems, we propose a Polarity Aggregation Model that takes into account both polarities guided by the geometrical mean. We study its performance by extracting aspects of monuments reviews and assigning to them the aggregated polarities. The advantage is that it matches together the sentiment of the context (User Polarity) and the sentiment extracted by a pre-trained method (SAM Polarity). We also show that this score fixes inconsistencies and it may be applied for discovering trustworthy insights from aspects, considering both general and specific context.